Best AI trading bot setup (paper trading first)
Updated · What changed: First published with Alpaca paper trading and TradingAgents as the picks.
By The AI Loadout editors · How we pick
The safest way to build an AI trading agent today is Claude Code connected to Alpaca's official MCP server on a free paper trading account. The MCP server defaults to paper trading, so the agent can check positions, pull market data and place practice orders for stocks, options and crypto without real money. Use TradingAgents as the research bot that proposes buy, hold or sell calls, and log those calls against the paper account for months before you trust anything. For crypto, see the crypto trading bot setup with Freqtrade. This page is educational only and is not financial advice.
| Slot | Pick |
|---|---|
| Tool | Alpaca (paper trading account) |
| Model | Claude Opus 5.5 (frontier) or Qwen 3.5 27B (local) |
| Skill | Alpaca MCP server (paper mode) |
| Persona | The Skeptical Trading Analyst |
| Bot | TradingAgents |
Free, no signup needed.
We check these picks every day. When one changes, it is in the next morning's email.
Free starter kit on signup: 2 Claude Code skills and 1 agent persona from our paid packs. By subscribing you agree to get The AI Loadout Daily, one email each morning. No spam, we never sell your email, and every email has a one-click unsubscribe link.
The loadout (why each pick)
Tool: Alpaca (paper trading account)
Alpaca's docs say a free paper trading account is enough to start with its Trading API MCP server, which works with Claude Desktop, Claude Code, Cursor, VS Code and Gemini CLI. The server covers account and positions, orders (market, limit, stop, trailing stop, brackets, multi-leg spreads), market data, screeners and watchlists. It defaults to paper and only trades real money if you set ALPACA_PAPER_TRADE=false with live keys.
Model: Claude Opus 5.5 (frontier) or Qwen 3.5 27B (local)
Most of the work here is writing and checking strategy and backtest code, so use a strong coding model. Opus 5.5 at max effort in Claude Code topped Terminal-Bench 4.0 per GenAI Brief in mid October 2026. To keep strategies and data on your own machine, run Qwen 3.5 27B or Gemma 4 26B in Ollama or LM Studio on a 24 to 32 GB computer (see our run AI locally setup).
Agent skills
- Alpaca MCP server (paper mode): Lets the agent read your paper account and place practice orders from chat. Keep keys in the MCP client env block, never in chat, as Alpaca's docs say.
- Backtest before every change: Ask the agent to write a backtest for every rule it suggests and to report the period, number of trades and worst drawdown. Freqtrade and Jesse ship backtesting if you would rather not write your own.
Bot persona: The Skeptical Trading Analyst
LLMs sound confident about markets. This persona forces risk limits, backtests and plain language about uncertainty.
Bot: TradingAgents
TradingAgents is an open-source multi-agent LLM framework that outputs a buy, hold or sell decision per ticker and date. It does not place orders, per an InvestingStack audit, which is what you want while you are learning: it proposes, you check it against paper results. Browse all bots.
Comparison table
| Option | Best for | Model(s) | Price | Free plan | Last checked |
|---|---|---|---|---|---|
| Alpaca MCP + Claude Code | Stocks, options and crypto, paper first | Any MCP client | Paper account free; Algo Trader Plus data $99/mo | Yes | |
| TradingAgents | Research decisions, no orders | Your LLM of choice | Free code; you pay LLM calls | Yes | |
| Freqtrade | Crypto strategy bots with dry-run | FreqAI (ML) | Free (GPL-3.0) | Yes | |
| Hummingbot | Crypto market making and arbitrage | Condor AI harness | Free (Apache 2.0) | Yes |
Prices come from the linked vendor or source page and can change. Check the vendor before you buy.
Copy this setup
Paste this persona into your tool's custom instructions or project instructions:
You help me research and test trading ideas on a PAPER account only. Never place a live order and never suggest disabling paper mode. For every idea: state the rule in one sentence, write a backtest, report the test period, number of trades, win rate and worst drawdown, and list three ways the result could be overfit. Every order you propose must include a position size of no more than 2 percent of the paper account and a stop. Say "I don't know" when you don't. Never promise or predict returns. Remind me this is not financial advice when I ask whether to buy or sell.- Open a free Alpaca paper trading account and create paper API keys.
- Add the Alpaca MCP server to Claude Code or Cursor with the keys in the env block, and leave paper mode on.
- Paste the Skeptical Trading Analyst persona into CLAUDE.md or your project instructions.
- Run TradingAgents on a short watchlist and log each decision with the date and price.
- Have the agent backtest any rule before it places a paper order, and review results weekly for at least a few months.
Alternatives by situation
- Crypto only: Use Freqtrade in dry-run mode. It has backtesting, FreqAI, a web UI and Telegram control. See the crypto trading bot setup.
- Keep everything local: Run TradingAgents with a local model in Ollama or LM Studio so no prompts leave your machine. Expect weaker reasoning than a frontier model.
- Real-time data: Alpaca's free data has a 15 minute delay over the REST API. Algo Trader Plus ($99/mo) adds all US exchanges and unlimited calls.
- Agent with live keys: Do not, until months of paper results. If you ever do, use trade-only keys, per-order and daily caps, a symbol allow list and a kill switch, as TradingAgentStack recommends.
What changed
- : Page launched with initial picks. Prices and features were checked on the official pages listed under Sources.
FAQ
What is the best AI trading bot?
There is no bot with reliable proven returns, so the best setup is one you can test safely. We pick Claude Code with the Alpaca MCP server on a paper account, plus TradingAgents for research. Not financial advice.
Can an AI trading bot make money?
We make no profit claims. Backtests and bot track records are hypothetical and often overfit, and real trading can lose money. Treat any bot promising fixed or guaranteed returns as a likely scam.
Is there a free AI trading bot?
Yes. TradingAgents, Freqtrade and Hummingbot are free and open source, and Alpaca paper accounts are free. You pay for hosting and any LLM calls.
What is paper trading?
Paper trading runs your strategy against live prices with fake money, so you can see how it behaves without risking any.
Sources
- Alpaca docs: Trading API MCP server
- Alpaca market data plans
- TradingAgents repository (GitHub)
- InvestingStack: 20 AI trading agents, an open-source audit
- Freqtrade README (GitHub)
- Hummingbot.org
- TradingAgentStack: open-source AI trading bots (Oct 23, 2026)
- GenAI Brief: best LLM for coding, October 2026
Disclosure: links marked "affiliate" may earn us a commission, and sponsored slots are always labeled. Neither affects our picks. Read our methodology.